Chatting with Llama 3
A data analytics company is developing an internal AI assistant to help employees quickly access technical information. As part of this project, they want to integrate Llama 3, and have asked you to test it.
To get started, you initialize the Llama 3 model locally and generate a response to a question.
The model path is already stored as a variable named llama_path.
Deze oefening maakt deel uit van de cursus
Working with Llama 3
Oefeninstructies
- Import the
Llamaclass fromllama_cpp. - Initialize an instance of
Llama, specifyingllama_pathas the path to the model file.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
# Import the Llama class
from llama_cpp import ____
# Initialize the Llama model
llm = ____(model_path=____)
question = "What is the most used database for data storage?"
response = llm(question)
print(response)